examples/pytorch/llm/run_infer.sh

python llm_infer.py \
    --device 0 \
    --model_type llama2-7b \
    --ckpt_path "runs/llama2-7b/vx_xxx/output_best/pytorch_model.bin" \
    --eval_human true
support llama2 (#393) * Unify sft and infer code into a single file * update llama2 sft infer 2023-07-19 17:34:27 +08:00			`python llm_infer.py \`
			`--device 0 \`
			`--model_type llama2-7b \`
ckpt output directory ignore .safetensors (#410) ckpt output file ignore .safetensors update 2023-07-25 19:27:11 +08:00			`--ckpt_path "runs/llama2-7b/vx_xxx/output_best/pytorch_model.bin" \`
support llama2 (#393) * Unify sft and infer code into a single file * update llama2 sft infer 2023-07-19 17:34:27 +08:00			`--eval_human true`